Gesture recognition method and gesture recognition device

1. A gesture recognition method comprising: obtaining a hand image, wherein the hand image comprises a gesture graphic; determining a reference point in the gesture graphic; determining a plurality of circular arc reference lines by using the reference point as a center; determining a plurality of intersection points of each of the circular arc reference lines intersecting with a boundary of the gesture graphic; determining whether at least two finger blocks of a plurality of finger blocks of the gesture graphic conform to an approaching trend according to the circular arc reference lines and the intersection points, and determining whether the at least two finger blocks in a selected range of the gesture graphic form a continuous graphic block; and when the at least two finger blocks of the gesture graphic conform to the approaching trend and form the continuous graphic block, determining that the hand image is a hand pinch image.

2. The gesture recognition method according to claim 1 , wherein the step of determining the reference point in the gesture graphic comprises: calculating an average of a plurality of coordinate values of the gesture graphic to obtain the reference point.

3. The gesture recognition method according to claim 1 , wherein the step of determining the circular arc reference lines by using the reference point as the center comprises: determining a farthest point corresponding to the reference point in the gesture graphic; and determining a plurality of radii having different lengths corresponding to the circular arc reference lines based on a connecting line between the reference point and the farthest point.

4. The gesture recognition method according to claim 3 , wherein the circular arc reference lines are respectively semi-circular arc lines, and the circular arc reference lines are spaced apart at an equal interval.

5. The gesture recognition method according to claim 1 , wherein the step of determining whether the at least two finger blocks of the gesture graphic conform to the approaching trend comprises: selecting one of the circular arc reference lines that has a highest intersection point number as a first recognition boundary; selecting another one circular arc reference line, which is the previous circular arc reference line to the circular arc reference line farthest from the reference point among the circular arc reference lines, as a second recognition boundary; and determining whether the at least two finger blocks of the gesture graphic between the first recognition boundary and the second recognition boundary conform to the approaching trend.

6. The gesture recognition method according to claim 5 , further comprising: from all the intersection points of each of the circular arc reference lines between the first recognition boundary and the second recognition boundary, selecting coordinates of two intersection points that are adjacent to each other and located in the gesture graphic and calculating their center point coordinates to be defined as a finger skeleton point; and determining whether the at least two finger blocks of the gesture graphic conform to the approaching trend according to a plurality of skeleton point connecting lines of the finger skeleton points.

7. The gesture recognition method according to claim 6 , wherein the step of determining whether the at least two finger blocks of the gesture graphic conform to the approaching trend according to the skeleton point connecting lines of the finger skeleton points comprises: respectively connecting the finger skeleton points in each of the finger blocks to determine the skeleton point connecting lines.

8. The gesture recognition method according to claim 6 , wherein the step of determining whether the at least two finger blocks of the gesture graphic conform to the approaching trend according to the skeleton point connecting lines of the finger skeleton points comprises: when at least two of the skeleton point connecting lines are approaching each other, determining that the at least two finger blocks of the gesture graphic conform to the approaching trend.

9. The gesture recognition method according to claim 1 , wherein the step of determining whether the at least two finger blocks in the selected range of the gesture graphic form the continuous graphic block comprises: selecting one circular arc reference line, which is the next circular arc reference line to the circular arc reference line having a highest intersection point number among the circular arc reference lines, as a third recognition boundary; selecting another one of the circular arc reference lines that is farthest from the reference point as a fourth recognition boundary; and determining whether the at least two finger blocks of the gesture graphic between the third recognition boundary and the fourth recognition boundary form the continuous graphic block.

10. The gesture recognition method according to claim 1 , wherein the hand image is a binarized image, and a region in the gesture graphic and a region outside the gesture graphic of the hand image have different pixel values.

11. A gesture recognition device comprising: an image capturing device configured to obtain a hand image, wherein the hand image comprises a gesture graphic; and a processor, electrically coupled to the image capturing device, configured to analyze the gesture graphic of the hand image to determine a reference point in the gesture graphic, wherein the processor determines a plurality of circular arc reference lines by using the reference point as a center, and determines a plurality of intersection points of each of the circular arc reference lines intersecting with a boundary of the gesture graphic, wherein the processor determines whether at least two finger blocks of a plurality of finger blocks of the gesture graphic conform to an approaching trend according to the circular arc reference lines and the intersection points, and determines whether the at least two finger blocks in a selected range of the gesture graphic form a continuous graphic block, wherein when the at least two finger blocks of the gesture graphic conform to the approaching trend and form the continuous graphic block, the processor determines that the hand image is a hand pinch image.

12. The gesture recognition device according to claim 11 , wherein the processor calculates an average of a plurality of coordinate values of the gesture graphic to obtain the reference point.

13. The gesture recognition device according to claim 11 , wherein the processor determines a farthest point corresponding to the reference point in the gesture graphic, and the processor determines a plurality of radii having different lengths corresponding to the circular arc reference lines based on a connecting line between the reference point and the farthest point.

14. The gesture recognition device according to claim 13 , wherein the circular arc reference lines are respectively semi-circular arc lines, and the circular arc reference lines are spaced apart at an equal interval.

15. The gesture recognition device according to claim 11 , wherein the processor selects one of the circular arc reference lines that has a highest intersection point number as a first recognition boundary, and the processor selects another one circular arc reference line, which is the previous circular arc reference line to the circular arc reference line farthest from the reference point among the circular arc reference lines, as a second recognition boundary, wherein the processor determines whether the at least two finger blocks of the gesture graphic between the first recognition boundary and the second recognition boundary conform to the approaching trend.

16. The gesture recognition device according to claim 15 , wherein, from all the intersection points of each of the circular arc reference lines between the first recognition boundary and the second recognition boundary, the processor selects coordinates of two intersection points that are adjacent to each other and located in the gesture graphic and calculates their center point coordinates to be defined as a finger skeleton point, and the processor determines whether the at least two finger blocks of the gesture graphic conform to the approaching trend according to a plurality of skeleton point connecting lines of the finger skeleton points.

17. The gesture recognition device according to claim 16 , wherein the processor respectively connects the finger skeleton points in each of the finger blocks to determine the skeleton point connecting lines.

18. The gesture recognition device according to claim 16 , wherein when at least two of the skeleton point connecting lines are approaching each other, the processor determines that the at least two finger blocks of the gesture graphic conform to the approaching trend.

19. The gesture recognition device according to claim 11 , wherein the processor selects one circular arc reference line, which is the next circular arc reference line to the circular arc reference line having a highest intersection point number among the circular arc reference lines, as a third recognition boundary, and the processor selects another one of the circular arc reference lines that is farthest from the reference point as a fourth recognition boundary, wherein the processor determines whether the at least two finger blocks of the gesture graphics between the third recognition boundary and the fourth recognition boundary form the continuous graphic block.

20. The gesture recognition device according to claim 11 , wherein the hand image is a binarized image, and a region in the gesture graphic and a region outside the gesture graphic of the hand image have different pixel values.